Segmenting, modeling, and matching video clips containing multiple moving objects
- 27 June 2004
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2 (10636919) , 914-921
- https://doi.org/10.1109/cvpr.2004.1315263
Abstract
This paper presents a novel representation for dynamic scenes composed of multiple rigid objects that may undergo different motions and be observed by a moving camera. Multi-view constraints associated with groups of affine-invariant scene patches and a normalized description of their appearance are used to segment a scene into its rigid parts, construct three-dimensional protective, affine, and Euclidean models of these parts, and match instances of models recovered from different image sequences. The proposed approach has been implemented, and it is applied to the detection and recognition of moving objects in video sequences and the identification of shots that depict the same scene in a video clip (shot matching).Keywords
This publication has 26 references indexed in Scilit:
- Matching Widely Separated Views Based on Affine Invariant RegionsInternational Journal of Computer Vision, 2004
- Efficient matching and clustering of video shotsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- RELIABLE TRANSITION DETECTION IN VIDEOS: A SURVEY AND PRACTITIONER'S GUIDEInternational Journal of Image and Graphics, 2001
- Performance characterization of video-shot-change detection methodsIEEE Transactions on Circuits and Systems for Video Technology, 2000
- Surface matching for object recognition in complex three-dimensional scenesImage and Vision Computing, 1998
- Token tracking in a cluttered sceneImage and Vision Computing, 1994
- A Combined Corner and Edge DetectorPublished by British Machine Vision Association and Society for Pattern Recognition ,1988
- The Representation, Recognition, and Locating of 3-D ObjectsThe International Journal of Robotics Research, 1986
- Efficient algorithms for interval graphs and circular‐arc graphsNetworks, 1982
- Random sample consensusCommunications of the ACM, 1981